{"id":"W2157202661","doi":"10.1111/j.1365-2929.2005.02092.x","title":"Assessment in the context of uncertainty: how many members are needed on the panel of reference of a script concordance test?","year":2005,"lang":"en","type":"article","venue":"Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":151,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Concordance; Cronbach's alpha; Statistics; Context (archaeology); Sample size determination; Reliability (semiconductor); Panel analysis; Test (biology); Panel data; Correlation; Sample (material); Medicine; Kappa; Mathematics; Psychometrics; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001137348,0.00008381788,0.0003053645,0.00004418546,0.00001742603,0.000004189775,0.0001936556,0.00008867334,0.0002463128],"category_scores_gemma":[0.1166776,0.00004400047,0.00005713831,0.00021821,0.0002997652,0.00001831161,0.0000161872,0.0003303691,0.000002607042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000609421,"about_ca_system_score_gemma":0.001337381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001114251,"about_ca_topic_score_gemma":0.0002076198,"domain_scores_codex":[0.9985157,0.0001375415,0.0004082901,0.0001395007,0.000681856,0.000117164],"domain_scores_gemma":[0.9859961,0.01295551,0.0003439996,0.0003835821,0.0002178192,0.0001029724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000537627,0.01490312,0.2162059,0.0004599239,0.0001279548,0.00001122206,0.01223973,0.00004824473,0.001364085,0.04307711,0.330138,0.3808871],"study_design_scores_gemma":[0.004108624,0.001686097,0.864007,0.01587677,0.0002064348,0.0000227942,0.08888622,0.004264582,0.002195771,0.0006938624,0.01784739,0.0002044764],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.835771,0.0001722977,0.00001770013,0.1607828,0.0001459115,0.000296978,0.000006781504,0.000004756522,0.002801852],"genre_scores_gemma":[0.9842082,0.0001404259,0.0001185056,0.01517779,0.00009822917,0.00004846857,0.0000176854,0.000005073658,0.0001856536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.647801,"threshold_uncertainty_score":0.890763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05041126147914685,"score_gpt":0.3757654797721233,"score_spread":0.3253542182929764,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}